OpenML
Filter results by:
1. Title: Glass Identification Database 2. Sources: (a) Creator: B. German -- Central Research Establishment Home Office Forensic Science Service Aldermaston, Reading, Berkshire RG7 4PN (b) Donor:…
1776 runs0 likes50 downloads50 reach9 impact
214 instances - 10 features - 6 classes - 0 missing values
This database encodes the complete set of possible board configurations at the end of tic-tac-toe games, where "x" is assumed to have played first. The target concept is "win for x" (i.e., true when…
386330 runs2 likes79 downloads81 reach10 impact
958 instances - 10 features - 2 classes - 0 missing values
No data.
965 runs0 likes9 downloads9 reach9 impact
55296 instances - 10 features - 3 classes - 0 missing values
No data.
867 runs0 likes12 downloads12 reach9 impact
39366 instances - 10 features - 2 classes - 0 missing values
1. Title: Contraceptive Method Choice 2. Sources: (a) Origin: This dataset is a subset of the 1987 National Indonesia Contraceptive Prevalence Survey (b) Creator: Tjen-Sien Lim (limt@stat.wisc.edu)…
23889 runs0 likes19 downloads19 reach10 impact
1473 instances - 10 features - 3 classes - 0 missing values
Current dataset was adapted to ARFF format from the UCI version. Sample code ID's were removed. ! Note that there is also a related Breast Cancer Wisconsin (Diagnosis) Data Set with a different set of…
28321 runs1 likes20 downloads21 reach9 impact
699 instances - 10 features - 2 classes - 16 missing values
Citation Request: This breast cancer domain was obtained from the University Medical Centre, Institute of Oncology, Ljubljana, Yugoslavia. Thanks go to M. Zwitter and M. Soklic for providing the data.…
2009 runs1 likes35 downloads36 reach9 impact
286 instances - 10 features - 2 classes - 9 missing values
PRO FOOTBALL SCORES (raw data appears after the description below) How well do the oddsmakers of Las Vegas predict the outcome of professional football games? Is there really a home field advantage -…
15930 runs0 likes19 downloads19 reach25 impact
672 instances - 10 features - 2 classes - 1200 missing values
A family of datasets synthetically generated from a simulation of how bank-customers choose their banks. Tasks are based on predicting the fraction of bank customers who leave the bank because of full…
0 runs0 likes6 downloads6 reach13 impact
8192 instances - 9 features - 0 classes - 0 missing values
* Title: Wholesale customers Data Set * Abstract: The data set refers to clients of a wholesale distributor. It includes the annual spending in monetary units (m.u.) on diverse product categories *…
161 runs0 likes10 downloads10 reach14 impact
440 instances - 9 features - 2 classes - 0 missing values
* Title: Nursery Database * Abstract: 4-class version of the original Nursery dataset
121 runs0 likes7 downloads7 reach14 impact
12958 instances - 9 features - 4 classes - 0 missing values
* Abstract: A 3-class version of abalone dataset. * Sources: (a) Original owners of database: Marine Resources Division Marine Research Laboratories - Taroona Department of Primary Industry and…
176 runs0 likes4 downloads4 reach14 impact
4177 instances - 9 features - 3 classes - 0 missing values
Concrete is the most important material in civil engineering. The concrete compressive strength is a highly nonlinear function of age and ingredients. These ingredients include cement, blast furnace…
3 runs1 likes3 downloads4 reach13 impact
1030 instances - 9 features - classes - 0 missing values
Twenty two observations of the Dwarf planet Ceres as observed by Giueseppe Piazzi and published in the September edition of Monatlicher Correspondenz in 1801. These were the measurements used by Gauss…
0 runs0 likes0 downloads0 reach10 impact
22 instances - 9 features - classes - 17 missing values
postoperative-patient-data-pmlb
26 runs0 likes1 downloads1 reach20 impact
88 instances - 9 features - 2 classes - 0 missing values
test001
0 runs1 likes0 downloads1 reach9 impact
768 instances - 9 features - classes - 0 missing values
Andrew V Uzilov, Joshua M Keegan, and David H Mathews. Detection of non-coding RNAs on the basis of predicted secondary structure formation free energy change. BMC Bioinformatics, 7(173), 2006. This…
31 runs0 likes10 downloads10 reach15 impact
488565 instances - 9 features - 2 classes - 0 missing values
test
0 runs0 likes0 downloads0 reach3 impact
4324 instances - 9 features - classes - 3360 missing values
diabetes
0 runs0 likes0 downloads0 reach6 impact
768 instances - 9 features - classes - 0 missing values
This is a family of datasets synthetically generated from a realistic simulation of the dynamics of a Unimation Puma 560 robot arm. There are eight datastets in this family . In this repository we…
2 runs0 likes5 downloads5 reach9 impact
8192 instances - 9 features - 0 classes - 0 missing values
analcatdata A collection of data sets used in the book "Analyzing Categorical Data," by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two…
2 runs0 likes0 downloads0 reach13 impact
74 instances - 9 features - 0 classes - 0 missing values
Chocolate Bar Ratings. Expert ratings of over 1,700 chocolate bars. Each chocolate is evaluated from a combination of both objective qualities and subjective interpretation. A rating here only…
0 runs0 likes1 downloads1 reach8 impact
1795 instances - 9 features - 42 classes - 1 missing values
Chocolate Bar Ratings. Expert ratings of over 1,700 chocolate bars. Each chocolate is evaluated from a combination of both objective qualities and subjective interpretation. A rating here only…
0 runs0 likes1 downloads1 reach8 impact
1794 instances - 9 features - 41 classes - 0 missing values
Relationship between IQ and Brain Size Summary: Monozygotic twins share numerous physical, psychological, and pathological traits. Recent advances in in vivo brain image acquisition and analysis have…
0 runs0 likes0 downloads0 reach13 impact
20 instances - 9 features - 0 classes - 0 missing values
This database was designed on the basis of data provided by US Census Bureau [http://www.census.gov] (under Lookup Access [http://www.census.gov/cdrom/lookup]: Summary Tape File 1). The data were…
2 runs1 likes3 downloads4 reach9 impact
22784 instances - 9 features - 0 classes - 0 missing values
This is data set is concerned with the forward kinematics of an 8 link robot arm. Among the existing variants of this data set we have used the variant 8nm, which is known to be highly non-linear and…
19 runs0 likes7 downloads7 reach9 impact
8192 instances - 9 features - 0 classes - 0 missing values
This dataset is taken from the Places Rated Almanac, by Richard Boyer and David Savageau, copyrighted and published by Rand McNally. This book order (SBN) number is 0-528-88008-X, and it retails for…
2 runs0 likes7 downloads7 reach13 impact
329 instances - 9 features - 0 classes - 0 missing values
Make target (age) numeric**Author**: 1. Title of Database: Abalone data 2. Sources: (a) Original owners of database: Marine Resources Division Marine Research Laboratories - Taroona Department of…
0 runs0 likes0 downloads0 reach0 impact
4177 instances - 9 features - 0 classes - 0 missing values
Incident reports from the San Franciso Police Department between January 2003 and May 2018, provided by the City and County of San Francisco. The dataset was downloaded on 05.11.2018. from…
0 runs0 likes0 downloads0 reach0 impact
2215023 instances - 9 features - 2 classes - 0 missing values
Contains 110 data sets from the book 'The Statistical Sleuth' by Fred Ramsey and Dan Schafer; Duxbury Press, 1997. (schafer@stat.orst.edu) [14/Oct/97] (172k) Note: description taken from this web…
0 runs0 likes0 downloads0 reach13 impact
34 instances - 9 features - 0 classes - 0 missing values
Normalized form of codrna (351) Andrew V Uzilov, Joshua M Keegan, and David H Mathews. Detection of non-coding RNAs on the basis of predicted secondary structure formation free energy change. BMC…
309 runs0 likes5 downloads5 reach9 impact
488565 instances - 9 features - 2 classes - 0 missing values
No data.
697 runs0 likes7 downloads7 reach15 impact
320 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
747 runs0 likes13 downloads13 reach15 impact
4177 instances - 9 features - 2 classes - 0 missing values
February 23, 1982 The 1982 annual meetings of the American Statistical Association (ASA) will be held August 16-19, 1982 in Cincinnati. At that meeting, the ASA Committee on Statistical Graphics plans…
759 runs0 likes9 downloads9 reach23 impact
209 instances - 9 features - 2 classes - 15 missing values
DATA-SETS FROM DIGGLE, P.J. (1990). TIME SERIES : A BIOSTATISTICAL INTRODUCTION. Oxford University Press. Table: Table A2 Wool prices Information about the dataset CLASSTYPE: numeric CLASSINDEX: none…
626 runs0 likes6 downloads6 reach14 impact
310 instances - 9 features - 9 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
760 runs0 likes13 downloads13 reach15 impact
8192 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
107 runs0 likes3 downloads3 reach14 impact
74 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
686 runs0 likes5 downloads5 reach15 impact
782 instances - 9 features - 2 classes - 466 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
723 runs0 likes5 downloads5 reach14 impact
34 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
589 runs0 likes12 downloads12 reach15 impact
22784 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
796 runs0 likes9 downloads9 reach15 impact
8192 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
756 runs0 likes6 downloads6 reach15 impact
310 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
581 runs0 likes11 downloads11 reach15 impact
20640 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
761 runs0 likes14 downloads14 reach15 impact
8192 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
119 runs0 likes4 downloads4 reach14 impact
95 instances - 9 features - 2 classes - 9 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
718 runs0 likes6 downloads6 reach15 impact
406 instances - 9 features - 2 classes - 14 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
721 runs0 likes5 downloads5 reach15 impact
412 instances - 9 features - 2 classes - 96 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
717 runs0 likes5 downloads5 reach14 impact
90 instances - 9 features - 2 classes - 3 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
652 runs0 likes17 downloads17 reach15 impact
12960 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
118 runs0 likes3 downloads3 reach15 impact
228 instances - 9 features - 2 classes - 20 missing values
S&P Letters Data We collected information on the variables using all the block groups in California from the 1990 Census. In this sample a block group on average includes 1425.5 individuals living in…
0 runs0 likes6 downloads6 reach13 impact
20640 instances - 9 features - 0 classes - 0 missing values
The dataset (originally named ELEC2) contains 45,312 instances dated from 7 May 1996 to 5 December 1998. Each example of the dataset refers to a period of 30 minutes, i.e. there are 48 instances for…
106854 runs3 likes38 downloads41 reach11 impact
45312 instances - 9 features - 2 classes - 0 missing values
1. Title of Database: Abalone data 2. Sources: (a) Original owners of database: Marine Resources Division Marine Research Laboratories - Taroona Department of Primary Industry and Fisheries, Tasmania…
34899 runs0 likes18 downloads18 reach9 impact
4177 instances - 9 features - 28 classes - 0 missing values
analcatdata A collection of data sets used in the book "Analyzing Categorical Data," by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two…
1187 runs1 likes10 downloads11 reach9 impact
412 instances - 9 features - 7 classes - 96 missing values
No data.
2198 runs1 likes16 downloads17 reach9 impact
1484 instances - 9 features - 10 classes - 0 missing values
1. Title: Pima Indians Diabetes Database 2. Sources: (a) Original owners: National Institute of Diabetes and Digestive and Kidney Diseases (b) Donor of database: Vincent Sigillito…
202119 runs6 likes89 downloads95 reach15 impact
768 instances - 9 features - 2 classes - 0 missing values
1. Title: Postoperative Patient Data 2. Source Information: -- Creators: Sharon Summers, School of Nursing, University of Kansas Medical Center, Kansas City, KS 66160 Linda Woolery, School of Nursing,…
1758 runs0 likes10 downloads10 reach9 impact
90 instances - 9 features - 3 classes - 3 missing values
1. Title: Nursery Database 2. Sources: (a) Creator: Vladislav Rajkovic et al. (13 experts) (b) Donors: Marko Bohanec (marko.bohanec@ijs.si) Blaz Zupan (blaz.zupan@ijs.si) (c) Date: June, 1997 3. Past…
2210 runs0 likes18 downloads18 reach11 impact
12960 instances - 9 features - 5 classes - 0 missing values
Grass Grubs and Damage Ranking Data source: R. J. Townsend AgResearch, Lincoln, New Zealand Grass grubs are one of the major insect pests of pasture in Canterbury and can cause severe pasture damage…
988 runs0 likes8 downloads8 reach15 impact
155 instances - 9 features - 4 classes - 0 missing values
analcatdata A collection of data sets used in the book "Analyzing Categorical Data," by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two…
104 runs0 likes4 downloads4 reach14 impact
52 instances - 9 features - 2 classes - 0 missing values
No data.
747 runs0 likes7 downloads7 reach15 impact
369 instances - 9 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
842 runs0 likes7 downloads7 reach15 impact
155 instances - 9 features - 2 classes - 0 missing values
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% This is a PROMISE Software Engineering Repository data set made publicly available in order to encourage repeatable,…
908 runs0 likes9 downloads9 reach14 impact
130 instances - 9 features - 2 classes - 0 missing values
No data.
748 runs0 likes7 downloads7 reach15 impact
274 instances - 9 features - 2 classes - 0 missing values
No data.
697 runs0 likes5 downloads5 reach14 impact
89 instances - 9 features - 2 classes - 0 missing values
File README ----------- chscase A collection of the data sets used in the book "A Casebook for a First Course in Statistics and Data Analysis," by Samprit Chatterjee, Mark S. Handcock and Jeffrey S.…
22 runs0 likes2 downloads2 reach14 impact
400 instances - 8 features - 0 classes - 0 missing values
Datasets of Data And Story Library, project illustrating use of basic statistic methods, converted to arff format by Hakan Kjellerstrand. Source: TunedIT: http://tunedit.org/repo/DASL DASL file…
0 runs0 likes2 downloads2 reach13 impact
48 instances - 8 features - 0 classes - 0 missing values
* Title: seeds Data Set * Abstract: Measurements of geometrical properties of kernels belonging to three different varieties of wheat. A soft X-ray technique and GRAINS package were used to construct…
190 runs0 likes5 downloads5 reach13 impact
210 instances - 8 features - 3 classes - 0 missing values
* Title: seismic-bumps Data Set * Abstract: The data describe the problem of high energy (higher than 10^4 J) seismic bumps forecasting in a coal mine. Data come from two of longwalls located in a…
152 runs0 likes37 downloads37 reach13 impact
210 instances - 8 features - 3 classes - 0 missing values
This database has been artificially generated. It describes the structure of the capital letters A, C, D, E, F, G, H, L, P, R, indicated by a number 1-10, in that order (A=1,C=2,...). Each letter's…
24309 runs0 likes10 downloads10 reach57 impact
10218 instances - 8 features - 10 classes - 0 missing values
"The debutanizer column is part of a desulfuring and naphtha splitter plant." u1 Top temperature u2 Top pressure u3 Reflux flow u4 Flow to next process u5 6th tray temperature u6 Bottom…
0 runs0 likes1 downloads1 reach11 impact
2394 instances - 8 features - 0 classes - 0 missing values
cars1-pmlb
31 runs0 likes3 downloads3 reach20 impact
392 instances - 8 features - 3 classes - 0 missing values
cleveland-nominal-pmlb
31 runs0 likes1 downloads1 reach20 impact
303 instances - 8 features - 5 classes - 0 missing values
ecoli-pmlb
31 runs0 likes1 downloads1 reach20 impact
327 instances - 8 features - 5 classes - 0 missing values
led7-pmlb
31 runs0 likes0 downloads0 reach21 impact
3200 instances - 8 features - 10 classes - 0 missing values
The goal is to predict the Fare. Variable description: pclass: A proxy for socio-economic status (SES) 1st = Upper 2nd = Middle 3rd = Lower age: Age is fractional if less than 1. If the age is…
0 runs0 likes4 downloads4 reach10 impact
1307 instances - 8 features - 0 classes - 0 missing values
Data
0 runs0 likes1 downloads1 reach10 impact
539383 instances - 8 features - 2 classes - 0 missing values
Test
0 runs0 likes0 downloads0 reach7 impact
6330 instances - 8 features - classes - 0 missing values
This data represents crime reported to the Seattle Police Department (SPD). Each row contains the record of a unique event where at least one criminal offense was reported by a member of the community…
0 runs0 likes0 downloads0 reach6 impact
52358 instances - 8 features - 0 classes - 650 missing values
Airlines Dataset Inspired in the regression dataset from Elena Ikonomovska. The task is to predict whether a given flight will be delayed, given the information of the scheduled departure. For this…
0 runs0 likes1 downloads1 reach6 impact
26969 instances - 8 features - 2 classes - 0 missing values
This is the hip measurement data from Table B.13 in Chatfield's Problem Solving (1995, 2nd edn, Chapman and Hall). It is given in 8 columns. First 4 columns are for Control Group. Last 4 columns are…
0 runs0 likes0 downloads0 reach11 impact
54 instances - 8 features - classes - 120 missing values
Graeme D. Hutcheson and Nick Sofroniou 1999 The Multivariate Social Scientist: Introductory Statistics Using Generalized Linear Models. SAGE Publications. Copyright: Graeme D. Hutcheson & Nick…
2 runs0 likes0 downloads0 reach13 impact
70 instances - 8 features - 0 classes - 0 missing values
test
0 runs0 likes0 downloads0 reach2 impact
336 instances - 8 features - classes - 0 missing values
xxx
0 runs0 likes0 downloads0 reach6 impact
891 instances - 8 features - classes - 689 missing values
xxx
0 runs0 likes0 downloads0 reach6 impact
891 instances - 8 features - 2 classes - 689 missing values
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Identifier attribute deleted. As used by Kilpatrick, D. & Cameron-Jones, M. (1998). Numeric prediction using instance-based…
2 runs0 likes2 downloads2 reach12 impact
398 instances - 8 features - 0 classes - 6 missing values
The data are a subsample of 500 observations from a data set that originate in a study where air pollution at a road is related to traffic volume and meteorological variables, collected by the…
2 runs0 likes1 downloads1 reach13 impact
500 instances - 8 features - 0 classes - 0 missing values
Airlines Dataset Inspired in the regression dataset from Elena Ikonomovska. The task is to predict whether a given flight will be delayed, given the information of the scheduled departure.
291 runs0 likes29 downloads29 reach16 impact
539383 instances - 8 features - 2 classes - 0 missing values
1. Title: Echocardiogram Data 2. Source Information: -- Donor: Steven Salzberg (salzberg@cs.jhu.edu) -- Collector: -- Dr. Evlin Kinney -- The Reed Institute -- P.O. Box 402603 -- Maimi, FL 33140-0603…
0 runs0 likes0 downloads0 reach8 impact
132 instances - 8 features - 4 classes - 103 missing values
File README ----------- chscase A collection of the data sets used in the book "A Casebook for a First Course in Statistics and Data Analysis," by Samprit Chatterjee, Mark S. Handcock and Jeffrey S.…
0 runs0 likes0 downloads0 reach13 impact
400 instances - 8 features - 0 classes - 0 missing values
The data are a subsample of 500 observations from a data set that originate in a study where air pollution at a road is related to traffic volume and meteorological variables, collected by the…
2 runs0 likes1 downloads1 reach13 impact
500 instances - 8 features - 0 classes - 0 missing values
analcatdata A collection of data sets used in the book "Analyzing Categorical Data," by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two…
0 runs0 likes1 downloads1 reach11 impact
228 instances - 8 features - classes - 20 missing values
This analysis describes and summarizes the relationships between 1987 salaries of major league baseball players and the player's performance. The salary data were taken from Sports Illustrated, April…
0 runs1 likes1 downloads2 reach13 impact
26 instances - 8 features - 0 classes - 0 missing values
This data represents crime reported to the Seattle Police Department (SPD). Each row contains the record of a unique event where at least one criminal offense was reported by a member of the community…
0 runs0 likes0 downloads0 reach8 impact
523590 instances - 8 features - 144 classes - 6916 missing values
exercises
0 runs0 likes0 downloads0 reach8 impact
15000 instances - 8 features - classes - 0 missing values
exercises
0 runs0 likes0 downloads0 reach8 impact
15000 instances - 8 features - classes - 0 missing values
Datasets for `Pattern Recognition and Neural Networks' by B.D. Ripley ===================================================================== Cambridge University Press (1996) ISBN 0-521-46086-7 The…
743 runs0 likes8 downloads8 reach15 impact
200 instances - 8 features - 2 classes - 0 missing values
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Weight treated as the class attribute. Identifier deleted. As used by Kilpatrick, D. & Cameron-Jones, M. (1998). Numeric…
10 runs0 likes2 downloads2 reach12 impact
158 instances - 8 features - 0 classes - 87 missing values
Data from StatLib (ftp stat.cmu.edu/datasets) Data from which conclusions were drawn in the article "Sleep in Mammals: Ecological and Constitutional Correlates" by Allison, T. and Cicchetti, D.…
0 runs0 likes1 downloads1 reach9 impact
62 instances - 8 features - 0 classes - 12 missing values
File README ----------- chscase A collection of the data sets used in the book "A Casebook for a First Course in Statistics and Data Analysis," by Samprit Chatterjee, Mark S. Handcock and Jeffrey S.…
0 runs0 likes0 downloads0 reach13 impact
400 instances - 8 features - 0 classes - 0 missing values